PhillyMac/fdr-merged-final

FDR Merged Model

This is a complete conversational model created by merging:

• Base Model: microsoft/DialoGPT-small
• LoRA Adapter: PhillyMac/fdr-lora-kaggle-v1

Usage

This model can be used directly with HuggingFace InferenceClient or transformers:

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PhillyMac/fdr-merged-final")
model = AutoModelForCausalLM.from_pretrained("PhillyMac/fdr-merged-final")

prompt = "### Instruction:\nWhat makes an effective leader?\n\n### Response:\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Or with InferenceClient:

from huggingface_hub import InferenceClient

client = InferenceClient(model="PhillyMac/fdr-merged-final", token="your_token")
response = client.text_generation(
    "What makes an effective leader?",
    max_new_tokens=200,
    temperature=0.7
)

Model Details

• Combined the conversational abilities of DialoGPT-small with FDR's leadership voice
• Trained on curated FDR leadership content
• Ready for production use in RAG systems
• Compatible with HuggingFace Inference API